Skip to Main Content
Catalogue Link
<a href="/ords/r/dev/fed_occ/home" class="t-Header-logo-link"><span class="apex-logo-text">Handbook</span></a>
Hidden Page Items
New
5
New
HE Unit Template
New
Machine Learning
New
ITECH3500 - Machine Learning
New
20260100
New
New
New
New
Course
New
Unit
New
New
2.2
New
New
2026-06-16
New
2026-06-16
New
Information Technology
New
New
New
New
Institute of Innovation, Science & Sustainability
New
Information Technology
New
Undergraduate
New
15
New
New
.125
New
020119
New
Artificial Intelligence
New
<a href="http://www.federation.edu.au/locate/unit/itech3500">020119 - Artificial Intelligence</a>
New
Graded (e.g. HD, D, C, etc)
New
7
New
Bachelor Degree
New
Advanced
New
New
New
New
1
New
New
New
New
New
false
New
New
New
<p>This unit provides you with an overview of contemporary trends in artificial learning. You will explore a wide range of topics, including classification, temporal analysis, and predictive analytics, and learn to utilise them to address applications in a variety of domains, such as computer vision and natural language processing.</p>
New
New
<p>Topics may include:<br>
Neural network architectures such as multi-layer perceptrons, convolutional neural networks and recurrent neural networks<br>
Advanced deep-learning architectures that address specific applications such as object detection, temporal predictions <br>
Advanced model training methodologies including loss functions, optimisers and their appropriate use<br>
Validation strategies</p>
New
true
New
<p>Where supplementary assessment is available a student must have failed overall in the Unit but gained a final mark of 45 per cent or above, has completed all major assessment tasks (including all sub-components where a task has multiple parts) as specified in the Unit Description and is not eligible for any other form of supplementary assessment.</p>
New
true
Hidden Page Items
Semester
Semester
0200
Year
Year
2026
Current Year
2026
Breadcrumb Positioning
Handbook
ITECH3500 - Machine Learning
Pseudo Breadcrumb
ITECH3500 - Machine Learning
Breadcrumb Type
Unit
Catalogue Term and Year
Version Text
You are viewing a version for
Semester
Semester 1
Semester 2
Summer Semester
Year
2026
Download PDF
RDS Holder
Overview
Key information
Requisites
Learning outcomes
Assessment
FedTASK
Parent Region
Overview
Unit description
<p>This unit provides you with an overview of contemporary trends in artificial learning. You will explore a wide range of topics, including classification, temporal analysis, and predictive analytics, and learn to utilise them to address applications in a variety of domains, such as computer vision and natural language processing.</p>
Unit content
<p>Topics may include:<br> Neural network architectures such as multi-layer perceptrons, convolutional neural networks and recurrent neural networks<br> Advanced deep-learning architectures that address specific applications such as object detection, temporal predictions <br> Advanced model training methodologies including loss functions, optimisers and their appropriate use<br> Validation strategies</p>
Key information
Institute / school:
Institute of Innovation, Science & Sustainability
Discipline:
Information Technology
Study level:
Undergraduate
Credit points:
15
EFTSL:
0.125
Field of education:
<a href="http://www.federation.edu.au/locate/unit/itech3500">020119 - Artificial Intelligence</a>
Grade scheme:
Graded (e.g. HD, D, C, etc)
Placement component:
No
Requisites
Prerequisite
<p>must have completed "<a href="/ords/r/dev/fed_occ/course?p6_code=ITECH2500" target="_blank">ITECH2500</a>"</p>
Corequisite
None
Exclusion
<p>must not have completed 1 of "<a href="/ords/r/dev/fed_occ/course?p6_code=ITECH2111" target="_blank">ITECH2111</a>" / "ITECH6111" / "<a href="/ords/r/dev/fed_occ/course?p6_code=ITECH7001" target="_blank">ITECH7001</a>"</p>
Learning outcomes
Learning outcomes
<p>On successful completion of this unit, students are expected to gain the following [K]nowledge, [S]kills and [A]pplication of knowledge & skills</p>
Learning Outcomes
Ref
Outcome
K1
<p>Identify and explain a range of deep-learning architectures and methodologies for solving complex problems;</p>
K2
<p>Recognize complex modelling scenarios such as potential biases in data, and noise and confounding factors that may impact model performance</p>
K3
<p>Critically evaluate merits and limitations of artificial intelligence architectures, including societal and environmental impacts</p>
S1
<p>Design and implement prototypical solutions to complex problems that meet industry guidelines, including strategies to mitigate assessed risks</p>
S2
<p>Develop methodologies to evaluate and monitor machine learning models, prior to and after deployment</p>
S3
<p>Develop methodologies to evaluate and monitor machine learning models, prior to and after deployment</p>
A1
<p>Demonstrate judgement in identifying and adapting machine-learning methodologies to meet requirements</p>
A2
<p>Effectively communicate machine-learning concepts or proposed solutions</p>
Assessment
Learning Tasks and Assessment
Ref
Learning task
Assessment type
Weighting
Learning outcomes assessed
1
<p>Weekly tasks including: quizzes and exercises</p>
<p>Quizzes and/or exercises</p>
<p>20% - 40%</p>
K1, K2, K3, S1, S2, S3
2
<p>Students will conduct research to identify the most appropriate methodology to address a complex problem, including appropriate data management strategies, addressing computational complexity and risks. Students will implement the solution and communicate their findings.</p>
<p>Practical works and accompanying report and/or presentation</p>
<p>60% - 80%</p>
S1, S2, S3, A1, A2
Supplementary assessment available:
Yes
Supplimentary assessment information:
<p>Where supplementary assessment is available a student must have failed overall in the Unit but gained a final mark of 45 per cent or above, has completed all major assessment tasks (including all sub-components where a task has multiple parts) as specified in the Unit Description and is not eligible for any other form of supplementary assessment.</p>
FedTASK
FedTASK
<p>Federation University recognises that students require key transferable employability skills to prepare them for their future workplace and society. FedTASKs (<strong>T</strong>ransferable <strong>A</strong>ttributes <strong>S</strong>kills and <strong>K</strong>nowledge) provide a targeted focus on five key, transferable Attributes, Skills, and Knowledge that are embedded within curriculum, developed gradually towards successful measures and interlinked with cross-discipline and co-operative learning opportunities.</p>
FedTASK
Description of FedTASK outcome
Level
FedTASK 1: Interpersonal
The ability to effectively communicate, interact and work with others both individually and in groups.
<p>Level 2 - Student demonstrates some independence within provided guidelines</p>
FedTASK 2: Leadership
The ability to apply professional skills and behaviours in leading others.
<p>Level 2 - Student demonstrates some independence within provided guidelines</p>
FedTASK 3: Critical Thinking and Creativity
The ability to work in complexity and ambiguity using imagination to create new ideas.
<p>Level 3 - Student works independently with limited guidance or works within self-determined guidelines appropriate to context</p>
FedTASK 4: Digital Literacy
The ability to work fluently across a range of tools and applications to achieve a range of skills.
<p>Level 3 - Student works independently with limited guidance or works within self-determined guidelines appropriate to context</p>
FedTASK 5: Sustainable and Ethical Mindset
The ability to consider and assess the consequences and impact of ideas and actions in enacting ethical and sustainable decisions.
<p>Level 3 - Student works independently with limited guidance or works within self-determined guidelines appropriate to context</p>
Key information
Institute / school:
Institute of Innovation, Science & Sustainability
Discipline:
Information Technology
Study level:
Undergraduate
Credit points:
15
EFTSL:
0.125
Field of education:
<a href="http://www.federation.edu.au/locate/unit/itech3500">020119 - Artificial Intelligence</a>
Grade scheme:
Graded (e.g. HD, D, C, etc)
Placement component:
No
Disclaimer
<em>Information in the Federation Handbook is correct at the time of publication. The University reserves the right to alter any course, unit, procedure or fee.</em>
Additional information
Add Info Static Text
Internal reference: ITECH3500 - U2.2